mcpField
M
Mathmind Mcp Server

Mathmind Mcp Server

Local
github.com/RunninghcmMedia & Design3Updated 64w ago

About Mathmind Mcp Server

MathMind MCP Server is an audio and video creation toolkit for people using MCP-compatible tools. It supports image- and video-based editing, subtitles, transcription, clips, and image-to-video generation through natural-language requests.

Key features

  1. 01Combine images or video clips
  2. 02Extract text from video links
  3. 03Recognize and add subtitles
  4. 04Cut video segments
  5. 05Generate video from images
  6. 06Add image overlays to video

Use cases

  1. 01Create a video from images with audio
  2. 02Add subtitles to an uploaded video
  3. 03Extract spoken or displayed text from video
  4. 04Cut a clip or place a logo overlay

MCP support

Exposes audio and video creation and editing tools to MCP clients over SSE. The server requires an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"MathMind-MCP-SERVER": {
"command": "uvx",
"args": [
],
"env": {
"x-api-key": "<x-api-key>"
}
}
}
}
Run commanduvx [email protected]
Environment variables to set
x-api-keySecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypi[email protected]

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

一、简介:

MathMind MCP Server提供了一个基于MCP协议的音视频创作工具箱。用户在任意支持MCP协议的工具中添加MathMind MCP服务,即可实现用自然语言描述进行音视频的创作与剪辑。

二、核心工具

序号工具中文名称工具英文名称工具介绍(中文)
1多张图片合成视频imgs2video将一张或多张图片合成一个视频,支持添加背景音乐、配音。
2多个视频合成视频video2video将一个或多段视频素材合成一个视频,支持上传背景音乐(非必填)、配音(非必填)合成新的视频。支持单独上传首、尾视频,固定视频首尾。支持设置封面图、支持配音音量控制、支持背景音乐自定义音量。
3视频文案提取video2txt实时提取视频中的文案,用户输入视频链接即可。建议上传5分钟以下的视频
4视频字幕识别subtitleDynamic上传视频,即可识别字幕并输出最终带字幕的视频。字幕支持设置字体与位置等。支持传入text文本。
5视频字幕识别任务查询taskFetch2输入工具subtitleDynamic输出的traceId即可获得添加了字幕以后的视频地址
6视频片段获取videoCutRandom输入视频链接,输入截取的起始和结束位置,即可截取视频片段
7图生视频imageGenVideo上传图片,输入提示词,即可生成视频,模型为VIDU。
支持实时生成和异步生成。当异步生成,则需要调用查询工具:videoTaskFetch
实时直接生成URL;
异步先只给traceId,用户需要调用videoTaskFetch
8图片画中画imgPip输入视频,为视频添加图片,如logo、视频提及内容等图片素材。
支持自定义素材的宽高、入场和出场的时间、动画以及显示的位置,非必填,取默认值。
9画中画任务查询cutTaskFetch上述imgPip只会返回ReqId,此时需要使用任务查询工具主动查询结果

三、快速开始

获取apikey

在MathMind开放平台注册并获取apikey,立即前往

SSE 调用方式

Windsurf

前往 Windsurf > Settings > Cascade > Add Server > Add custom server 添加配置:

{
  "mcpServers": {
    "mcp-server-mathmind": {
      "url": "https://mcp.mathmind.cn/sse?x-api-key=<YOUR_API_KEY>"
    }
  }
}
Cursor

前往 Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server 添加配置:

{
  "mcpServers": {
    "mcp-server-mathmind": {
      "url": "https://mcp.mathmind.cn/sse?x-api-key=<YOUR_API_KEY>"
    }
  }
}
通义灵码

前往 通义灵码 -> MCP工具 -> MCP服务 -> 通过配置文件添加新增MCP服务 -> lingma_mcp.json添加以下配置:

{
  "mcpServers": {
    "mcp-server-mathmind": {
      "url": "https://mcp.mathmind.cn/sse?x-api-key=<YOUR_API_KEY>"
    }
  }
}

其他

技术支持

邮件联系:[email protected]

技术支持:

image

快捷入口

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.